1. Chart data
  2. OpenAI
  3. Recent released open weight models compare to frontier model
OpenAILine chart · 60 points · Codex

Recent released open weight models compare to frontier models

The numbers behind a chart OpenAI published, redrawn natively. Check the original, study the data, then make your own.

Estimated from the image 46%GPT-5.6All OpenAI modelsAll chart data
Chart by OpenAI. Source: x.com

Simplified redraw

Drawn by us from the numbers below. Hover, tap or use the arrow keys.

A simplified redraw: it shows the numbers in our own look, not the look of the original. One accent marks what the chart is about. Values marked with ~ in the table are estimates.

The numbers

First 10 of 60 points are free
GroupSeriesxValue (steps)SourceConf.
10kGPT-5.6-Sol (best attempt)10000~0Estimate0.80
100kGPT-5.6-Sol (best attempt)100000~2Estimate0.80
1MGPT-5.6-Sol (best attempt)1000000~5Estimate0.30
10MGPT-5.6-Sol (best attempt)10000000~10Estimate0.30
100MGPT-5.6-Sol (best attempt)100000000~32Estimate0.30
10kClaude Mythos 5 (best attempt)10000~0Estimate0.80
100kClaude Mythos 5 (best attempt)100000~2Estimate0.80
1MClaude Mythos 5 (best attempt)1000000~5Estimate0.80
10MClaude Mythos 5 (best attempt)10000000~12Estimate0.80
100MClaude Mythos 5 (best attempt)100000000~32Estimate0.30

Max data, free with your email for now

See all 60 points and download the files

The full table, the JSON, a CSV and the agent skill file for this chart. These are Max in the plan; while this is a prototype your email unlocks them.

Unlocks all 35 giants. One email a week, leave any time. What you get · Log in

10kMythos 5 10x100M10000~0Estimate0.80
100kMythos 5 10x100M100000~2Estimate0.30
1MMythos 5 10x100M1000000~5Estimate0.30
10MMythos 5 10x100M10000000~10Estimate0.30
100MMythos 5 10x100M100000000~30Estimate0.30
10kGPT-5.6-Sol 10x100M10000~0Estimate0.30
100kGPT-5.6-Sol 10x100M100000~2Estimate0.30
1MGPT-5.6-Sol 10x100M1000000~5Estimate0.30
10MGPT-5.6-Sol 10x100M10000000~10Estimate0.30
100MGPT-5.6-Sol 10x100M100000000~28Estimate0.30
10kClaude Mythos 5 10x100M10000~0Estimate0.30
100kClaude Mythos 5 10x100M100000~2Estimate0.30
1MClaude Mythos 5 10x100M1000000~5Estimate0.30
10MClaude Mythos 5 10x100M10000000~10Estimate0.30
100MClaude Mythos 5 10x100M100000000~26Estimate0.30
10kClaude Opus 4.6 10x100M10000~0Estimate0.80
100kClaude Opus 4.6 10x100M100000~2Estimate0.80
1MClaude Opus 4.6 10x100M1000000~5Estimate0.80
10MClaude Opus 4.6 10x100M10000000~10Estimate0.80
100MClaude Opus 4.6 10x100M100000000~24Estimate0.30
10kOpus 4.5 10x100M10000~0Estimate0.80
100kOpus 4.5 10x100M100000~2Estimate0.80
1MOpus 4.5 10x100M1000000~5Estimate0.30
10MOpus 4.5 10x100M10000000~10Estimate0.30
100MOpus 4.5 10x100M100000000~20Estimate0.30
10kSonnet 4.5 10x100M10000~0Estimate0.80
100kSonnet 4.5 10x100M100000~2Estimate0.80
1MSonnet 4.5 10x100M1000000~5Estimate0.30
10MSonnet 4.5 10x100M10000000~10Estimate0.30
100MSonnet 4.5 10x100M100000000~18Estimate0.30
10kGLM-5.2 10x100M10000~0Estimate0.80
100kGLM-5.2 10x100M100000~2Estimate0.80
1MGLM-5.2 10x100M1000000~5Estimate0.30
10MGLM-5.2 10x100M10000000~10Estimate0.30
100MGLM-5.2 10x100M100000000~12Estimate0.30
10kDeepSeek-V4-Pro 10x100M10000~0Estimate0.80
100kDeepSeek-V4-Pro 10x100M100000~2Estimate0.80
1MDeepSeek-V4-Pro 10x100M1000000~5Estimate0.30
10MDeepSeek-V4-Pro 10x100M10000000~10Estimate0.30
100MDeepSeek-V4-Pro 10x100M100000000~10Estimate0.30
10kMythos Preview 10x100M10000~0Estimate0.30
100kMythos Preview 10x100M100000~2Estimate0.30
1MMythos Preview 10x100M1000000~7Estimate0.30
10MMythos Preview 10x100M10000000~18Estimate0.30
100MMythos Preview 10x100M100000000~26Estimate0.30
10kGPT-5.5-Sol 10x100M10000~0Estimate0.30
100kGPT-5.5-Sol 10x100M100000~2Estimate0.30
1MGPT-5.5-Sol 10x100M1000000~6Estimate0.30
10MGPT-5.5-Sol 10x100M10000000~15Estimate0.30
100MGPT-5.5-Sol 10x100M100000000~24Estimate0.30
Download this chart's data

Max subscribers get the same data by API. API docs

JSONAgent skill file

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id 9a9adc45003e.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.46 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/9a9adc45003eTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/9a9adc45003e/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/9a9adc45003e/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/9a9adc45003e/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

Make one like this

This chart's shape, your numbers.

Live preview. Everything stays on your device.

Pick the form

A simplified form: our own look, not the look of the original. Your numbers start from this chart's data.

More data from OpenAI

All chart data
Estimated from the imageReplica 7.4TerminalBench 2.1OpenAI · Bar chart · 9 pointsEstimated from the imageReplica 8.1Illustrative global managed assetsOpenAI · Grouped bar chart · 22 pointsEstimated from the imageReplica 8.1Illustrative global managed assetsOpenAI · Grouped bar chart · 22 pointsPartly publisher's numbersReplica 8.3Accuracy / Percentile (%)deepseek · Benchmark bar chart · 30 pointsEstimated from the imageModel Benchmark ComparisonOpenAI · Table chart · 42 pointsEstimated from the imageGPT4 Turbo Benchmark ComparisonOpenAI · Line chart · 12 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.46 on a 0 to 1 scale. Printed numbers read well; values read off an axis can be a few percent off.

Can I reuse this data?

The numbers describe a chart that OpenAI published. The image, layout and styling belong to them. Use the numbers with a credit to the publisher, and make your picture from your own data.

How do I get the file?

The JSON, CSV and agent skill file are under the email gate on this page. In this prototype they are static files at /api/charts/9a9adc45003e.json and /api/charts/9a9adc45003e.skill.md.